Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add openephemeris/openephemeris-MCP --skill openephemerisgit clone --depth 1 https://github.com/openephemeris/openephemeris-MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/openephemeris/openephemeris-mcp/openephemeris)<a href="https://agentmods.dev/skills/openephemeris/openephemeris-mcp/openephemeris"><img src="https://agentmods.dev/badge/skills/openephemeris/openephemeris-mcp/openephemeris/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/openephemeris/openephemeris-mcp/openephemeris"><img src="https://agentmods.dev/badge/skills/openephemeris/openephemeris-mcp/openephemeris.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00109 | $0.04301 |
| Opus 5 | $0.00055 | $0.02150 |
| Sonnet 5 | $0.00022 | $0.00860 |
| Haiku 4.5 | $0.00011 | $0.00430 |
Grade A, and why
openephemeris scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenEphemeris — AI-Native Astrology
This skill turns Claude into a professional astrologer backed by NASA mission-grade planetary data. Ask about your birth chart, check today's transits, explore relationship compatibility, find auspicious timing for decisions, or generate a Human Design bodygraph — all in natural conversation, computed to real precision instead of guessed.
Every calculation uses the JPL DE440 planetary ephemeris — NASA mission-grade data covering 1,100 years of astronomical history — and our high-precision mathematical engine. These are not horoscope generators — they are astronomically accurate planetary positions, house cusps, and aspect geometry that Claude interprets for you in plain language.
House systems: Placidus by default — Whole Sign, Equal, Koch, Campanus, Regiomontanus, and Porphyry also available. Just ask.
Setup
1. Get an API Key
- Go to openephemeris.com/login?signup=true
- Create a free account (Explorer tier: 150 free credits one-time, no credit card)
- Go to Dashboard → Account tab → Create API Key
- Copy the key (starts with
oe_...)
Don't hardcode your API key. Set it as an environment variable.
2. Set Your API Key
export OPENEPHEMERIS_API_KEY="oe_your_key_here"
Or add to your shell profile (~/.bashrc, ~/.zshrc, etc.) for persistence.
3. Install the Plugin
claude plugin add openephemeris
Or if testing locally:
claude plugin add ./path/to/openephemeris
That's it. Ask Claude anything about astrology and it will compute real answers.
CRITICAL: Timezone & Time Precision Handling
Astrology requires exact time calculation. You must be rigorous with user time input:
- Never Assume AM/PM: If a user says "8:00", explicitly ask if it is AM or PM before generating anything.
- Local Time vs Timezone: Clarify if the time provided is local to the birth/event location. (e.g., "Was 8:00 PM the local time in Paris?").
- Timezone Offset: When computing the chart or using tools, ensure you understand the Daylight Saving Time (DST) or timezone rules for that specific year and location.
- Always state the zone: A datetime that names a clock time but not its zone is rejected — it is never assumed to be UTC. Either pass the local wall-clock time together with the
timezoneargument (datetime='1990-04-15T14:30:00',timezone='America/Chicago'— preferred, since the IANA zone resolves that year's DST for you), or put the offset on the value itself (1990-04-15T14:30:00-05:00, or...T19:30:00Zfor UTC). A date with no clock time (1990-04-15) is fine and resolves to noon UTC.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago Changed · +2 lines · +54 tokens per session f58c43ec84fd
- 12d ago First seen · 319 lines · 55 tokens per session scan A 59760df67a40
openephemeris is a skill published in the GitHub repository openephemeris/openephemeris-MCP (4 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 4,301 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
panchanga-api
Vedic astrology (Jyotish) REST API powered by Swiss Ephemeris. 19 endpoints: Panchanga, Kundali (300+ Yogas, Ashtakavarga, Doshas), KP system (249 sub-lords), Dasha, Muhurta, Choghadiya, Compatibility, Transits, Vrata calendar, Remedies, Panchanga Search, and more. All calculations use Lahiri ayanamsha and sidereal…
oraclaw-cmaes
CMA-ES continuous optimization for AI agents. State-of-the-art derivative-free optimizer. 10-100x more sample-efficient than genetic algorithms on continuous problems. Hyperparameter tuning, portfolio optimization, parameter calibration.
oraclaw-anomaly
Anomaly detection for AI agents. Z-score, IQR, and streaming detection. Find outliers in data instantly. Sub-millisecond response. Works on single values or full datasets.
oraclaw-bayesian
Bayesian inference engine for AI agents. Update beliefs with new evidence. Prior + evidence = posterior. Multi-factor prediction with calibration tracking.
oraclaw-calibrate
Prediction quality scoring for AI agents. Brier score, log score, and multi-source convergence analysis. Know if your forecasts are accurate and if your data sources agree.
oraclaw-forecast
Time series forecasting for AI agents. ARIMA and Holt-Winters predictions with confidence intervals. Predict revenue, traffic, prices, or any sequential data. Sub-5ms inference.